Intrauterine adhesions with symptoms like hypomenorrhea or infertility are known under the term Asherman's syndrome. Although the syndrome has been widely investigated, evidence of both prevention of the syndrome and the ideal treatment are missing. Understanding the pathogenesis of intrauterine adherences is necessary for the prevention of the formation of intrauterine scarring. Intrauterine adhesions can develop from lesion of the basal layer of the endometrium caused by curettage of the newly pregnant uterus. The syndrome may also occur after hysteroscopic surgery, uterine artery embolization or uterine tuberculosis. For initial diagnosis the less invasive contrast sonohysterography or hysterosalpingography is useful. The final diagnosis is based on hysteroscopy. Magnetic resonance imaging is required in cases with totally obliterated uterine cavity. Intrauterine adherences are classified in accordance with different classification systems based on the hysteroscopic diagnosis of severity and localization of adherences. Classification is necessary for the planning of surgery, information on prognosis and scientific purposes. Surgery is performed in symptomatic patients with either infertility or with painful periods. Intrauterine adherences are divided with a hysteroscope using scissors or a power instrument working from the central part of the uterus to the periphery. Peroperative ultrasonography is useful in an outpatient setting for the prevention of complications. Hysteroscopy with fluoroscopy is a solution in difficult cases. Use of intrauterine devices like balloon catheters or intrauterine contraceptive devices seems to be the preferred methods for the prevention of re-occurrence of adhesions after treatment. Both primary prevention after hysteroscopic surgery or curettage and secondary prevention of new adhesions after adhesiolysis have been investigated. The aim of this review was to summarize the literature on diagnosis, classification, treatment and prevention, based on a literature search with a wide range of search terms.

To develop a multimodal learning application system that integrates electronic medical records (EMR) and hysteroscopic images for reproductive outcome prediction and risk stratification of patients with intrauterine adhesions (IUAs) resulting from endometrial injuries.EMR and 5014 revisited hysteroscopic images of 753 post hysteroscopic adhesiolysis patients from the multicenter IUA database we established were randomly allocated to training, validation, and test datasets. The respective datasets were used for model development, tuning, and testing of the multimodal learning application. MobilenetV3 was employed for image feature extraction, and XGBoost for EMR and image feature ensemble learning. The performance of the application was compared against the single-modal approaches (EMR or hysteroscopic images), DeepSurv and ElasticNet models, along with the clinical scoring systems. The primary outcome was the 1-year conception prediction accuracy, and the secondary outcome was the assisted reproductive technology (ART) benefit ratio after risk stratification.The multimodal learning system exhibited superior performance in predicting conception within 1-year, achieving areas under the curves of 0.967 (95% CI: 0.950-0.985), 0.936 (95% CI: 0.883-0.989), and 0.965 (95% CI: 0.935-0.994) in the training, validation, and test datasets, respectively, surpassing single-modal approaches, other models and clinical scoring systems (all P<0.05). The application of the model operated seamlessly on the hysteroscopic platform, with an average analysis time of 3.7±0.8 s per patient. By employing the application's conception probability-based risk stratification, mid-high-risk patients demonstrated a significant ART benefit (odds ratio=6, 95% CI: 1.27-27.8, P=0.02), while low-risk patients exhibited good natural conception potential, with no significant increase in conception rates from ART treatment (P=1).The multimodal learning system using hysteroscopic images and EMR demonstrates promise in accurately predicting the natural conception of patients with IUAs and providing effective postoperative stratification, potentially contributing to ART triage after IUA procedures.Copyright © 2024 The Author(s). Published by Wolters Kluwer Health, Inc.

What are the factors influencing the fertility of patients with intrauterine adhesions (IUA) after hysteroscopic adhesiolysis and which assessment system is more efficient in predicting post-operative ongoing pregnancy?The clinical information of 369 individuals diagnosed with and treated for IUA were obtained from the Multicentre Prospective Clinical Database for the Construction of Predictive Models on Risk of Intrauterine Adhesion (NCT05381376) and randomly divided into the training and validation cohorts. A univariate analysis was performed to identify relevant clinical indicators, followed by a least absolute shrinkage and selection operator (LASSO) regression for regularization and SHapley Additive exPlanation (SHAP) for extreme gradient boosting (XGBoost) predictive model visualization. Finally, receiver operating characteristic (ROC) curves were constructed to assess the model's efficiency.Univariate analysis and LASSO regression demonstrated that 12 clinical indicators were significantly associated with post-operative ongoing pregnancy in IUA patients. SHAP visualization indicated that post-operative Fallopian tube ostia, blood supply, uterine cavity shape and age had the highest significance. The area under the ROC curve (AUC) of the XGBoost model in the training and validation cohorts was 0.987 (95% CI 0.979-0.996) and 0.985 (95% CI 0.967-1), respectively. These values were significantly higher than those of the American Fertility Society (AFS) classification, the Chinese Society for Gynecological Endoscopy (CSGE) classification and endometrial thickness (all P < 0.001).The XGBoost model had higher accuracy in predicting post-operative reproductive outcomes in IUA patients. Clinically, the model may be useful for managing and categorizing IUA and determining optimal action to aid in pregnancy.Copyright © 2023 Reproductive Healthcare Ltd. Published by Elsevier Ltd. All rights reserved.

Early reproductive failure is the most common complication of pregnancy with only 30% of conceptions reaching live birth. Establishing a successful pregnancy depends upon implantation, a complex process involving interactions between the endometrium and the blastocyst. It is estimated that embryos account for one-third of implantation failures, while suboptimal endometrial receptivity and altered embryo-endometrial dialogue are responsible for the remaining two-thirds. Endometrial receptivity has been the focus of extensive research for over 80 years, leading to an indepth understanding of the processes associated with embryo-endometrial cross-talk and implantation. However, little progress has been achieved to translate this understanding into clinically meaningful prognostic tests and treatments for suboptimal endometrial receptivity.The objective of this systematic review was to examine the evidence from observational studies supporting the use of endometrial receptivity markers as prognostic factors for pregnancy outcome in women wishing to conceive, in order to aid clinicians in choosing the most useful marker in clinical practice and for informing further research.The review protocol was registered with PROSPERO (CRD42017077891). MEDLINE and Embase were searched for observational studies published from inception until 26 February 2018. We included studies that measured potential markers of endometrial receptivity prior to pregnancy attempts and reported the subsequent pregnancy outcomes. We performed association and accuracy analyses using clinical pregnancy as an outcome to reflect the presence of receptive endometrium. The Newcastle-Ottawa scale for observational studies was employed to assess the quality of the included studies.We included 163 studies (88 834 women) of moderate overall quality in the narrative synthesis, out of which 96 were included in the meta-analyses. Studies reported on various endometrial receptivity markers evaluated by ultrasound, endometrial biopsy, endometrial fluid aspirate and hysteroscopy in the context of natural conception, IUI and IVF. Associations were identified between clinical pregnancy and various endometrial receptivity markers (endometrial thickness, endometrial pattern, Doppler indices, endometrial wave-like activity and various molecules); however, their poor ability to predict clinical pregnancy prevents them from being used in clinical practice. Results from several modern molecular tests are promising and further data are awaited.The post-test probabilities from our analyses may be used in clinical practice to manage couples' expectations during fertility treatments (IUI and IVF). Conventionally, endometrial receptivity is seen as a dichotomous outcome (present or absent), but we propose that various levels of endometrial receptivity exist within the window of implantation. For instance, different transcriptomic signatures could represent varying levels of endometrial receptivity, which can be linked to different pregnancy outcomes. Many studies reported the means of a particular biomarker in those who achieved a pregnancy compared with those who did not. However, extreme values of a biomarker (as opposite to the means) may have significant prognostic and diagnostic implications that are not captured in the means. Therefore, we suggest reporting the outcomes by categories of biomarker levels rather than reporting means of biomarker levels within clinical outcome groups.© The Author(s) 2019. Published by Oxford University Press on behalf of the European Society of Human Reproduction and Embryology. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

A detailed assessment of the uterus forms a pivotal part of the ART treatment process. The emergence of three-dimensional ultrasound (3D US) has provided clinicians with a highly powerful tool in this respect. Assessments with 3D US range from the reconstruction of anatomical planes elusive to conventional US, to the objective measurement of anatomical volumes and vascularization parameters. However, despite the ever increasing number of publications emerging in the literature, the question of which aspects of 3D US are of most clinical value remains a topic of debate.The objective of this review is to dissect which aspects of the 3D US assessment of the uterus are supported by a strong level of evidence to date, and should therefore be incorporated into current routine clinical practice.We conducted a systematic search of the PubMed database up to May 2016, using a combination of text words and Medical Subject Headings (MeSH) pertaining to the 3D US assessment of the uterus. All articles published in the English language were screened to ascertain relevance to women of reproductive age; further citations were retrieved through manual reference list searching.A multitude of predominantly observational studies were identified, which concerned a vast variety of 3D US uterine assessments. All articles unequivocally praised the non-invasive, cost-effective, highly acceptable and objective nature of 3D US. Studies regarding the value of assessing the endometrial volume and vascularization prior to embryo transfer appeared conflicting and inconsistent. Studies regarding the imaging of uterine pathology and identification of intratubal and intrauterine devices consistently reported high rates of diagnostic accuracy. A recent RCT did not show an improvement in clinical outcomes when comparing 3D versus 2D US during embryo transfer. However, preliminary studies suggested that 3D US is superior in determining the site of implantation, particularly in ambiguous cases such as interstitial and angular pregnancies. Finally, pilot studies have suggested that the further integration of 3D and possibly 4D US with surgical interventions of the uterus may be a promising prospect.3D US may prove to be an invaluable tool in the assessment of the uterus within the context of ART. Currently, the aim should be to highlight the aspects of 3D US that are most evidence-based and valuable for patients, and to incorporate these into routine clinical practice.© The Author 2016. Published by Oxford University Press on behalf of the European Society of Human Reproduction and Embryology. All rights reserved. For Permissions, please email: journals.permissions@oup.com

Intrauterine adhesions (IUAs) caused by endometrial injury, commonly occurring in developing countries, can lead to subfertility. This study aimed to develop and evaluate a DeepSurv architecture-based artificial intelligence (AI) system for predicting fertility outcomes after hysteroscopic adhesiolysis.

After treatment of intrauterine adhesions, the rate of re-adhesion is high and the pregnancy outcome unpredictable and unsatisfactory. This study established and verified a decision tree predictive model of live birth in patients after surgery for moderate-to-severe intrauterine adhesions (IUAs).

Occult nodal metastasis (ONM) plays a significant role in comprehensive treatments of non-small cell lung cancer (NSCLC). This study aims to develop a deep learning signature based on positron emission tomography/computed tomography to predict ONM of clinical stage N0 NSCLC. An internal cohort (n = 1911) is included to construct the deep learning nodal metastasis signature (DLNMS). Subsequently, an external cohort (n = 355) and a prospective cohort (n = 999) are utilized to fully validate the predictive performances of the DLNMS. Here, we show areas under the receiver operating characteristic curve of the DLNMS for occult N1 prediction are 0.958, 0.879 and 0.914 in the validation set, external cohort and prospective cohort, respectively, and for occult N2 prediction are 0.942, 0.875 and 0.919, respectively, which are significantly better than the single-modal deep learning models, clinical model and physicians. This study demonstrates that the DLNMS harbors the potential to predict ONM of clinical stage N0 NSCLC.© 2023. The Author(s).